Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    names of people with associated titles or professions

    oai_token-act-pair · gpt-3.5-turbo

    statements introducing individuals and their professions or roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LOD
    -0.75
    Side
    -0.73
    aceae
    -0.73
    addons
    -0.72
    Therefore
    -0.69
     dstg
    -0.67
    Materials
    -0.67
    Relations
    -0.66
    Decre
    -0.65
    Whereas
    -0.64
    POSITIVE LOGITS
     Editor
    0.85
     freelance
    0.77
     PhD
    0.75
     Slate
    0.73
     QC
    0.72
     pseudonym
    0.71
     Pulitzer
    0.71
     Jr
    0.71
    elaide
    0.69
     associate
    0.69
    Act Density 0.178%

    No Known Activations